InĀ [7]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt 
import seaborn as sns
import plotly.express as px
from plotly.subplots import make_subplots 
from datetime import datetime
InĀ [8]:
covid_df = pd.read_csv("C:\\Users\\KHUSHI\\Downloads\\Covid-19-Data-Analysis\\covid_19_india.csv")
InĀ [9]:
covid_df.head(10)
Out[9]:
Sno Date Time State/UnionTerritory ConfirmedIndianNational ConfirmedForeignNational Cured Deaths Confirmed
0 1.0 2020-01-30 6:00 PM Kerala 1 0 0.0 0.0 1.0
1 2.0 2020-01-31 6:00 PM Kerala 1 0 0.0 0.0 1.0
2 3.0 2020-02-01 6:00 PM Kerala 2 0 0.0 0.0 2.0
3 4.0 2020-02-02 6:00 PM Kerala 3 0 0.0 0.0 3.0
4 5.0 2020-02-03 6:00 PM Kerala 3 0 0.0 0.0 3.0
5 6.0 2020-02-04 6:00 PM Kerala 3 0 0.0 0.0 3.0
6 7.0 2020-02-05 6:00 PM Kerala 3 0 0.0 0.0 3.0
7 8.0 2020-02-06 6:00 PM Kerala 3 0 0.0 0.0 3.0
8 9.0 2020-02-07 6:00 PM Kerala 3 0 0.0 0.0 3.0
9 10.0 2020-02-08 6:00 PM Kerala 3 0 0.0 0.0 3.0
InĀ [13]:
covid_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 15114 entries, 0 to 15113
Data columns (total 9 columns):
 #   Column                    Non-Null Count  Dtype  
---  ------                    --------------  -----  
 0   Sno                       15086 non-null  float64
 1   Date                      15086 non-null  object 
 2   Time                      15086 non-null  object 
 3   State/UnionTerritory      15086 non-null  object 
 4   ConfirmedIndianNational   15086 non-null  object 
 5   ConfirmedForeignNational  15086 non-null  object 
 6   Cured                     15086 non-null  float64
 7   Deaths                    15086 non-null  float64
 8   Confirmed                 15086 non-null  float64
dtypes: float64(4), object(5)
memory usage: 1.0+ MB
InĀ [15]:
covid_df.describe()
Out[15]:
Sno Cured Deaths Confirmed
count 15086.000000 1.508600e+04 15086.000000 1.508600e+04
mean 7543.500000 1.747937e+05 2721.084449 1.942820e+05
std 4355.097416 3.648330e+05 7182.672358 4.095184e+05
min 1.000000 0.000000e+00 0.000000 0.000000e+00
25% 3772.250000 1.685000e+03 12.000000 2.935500e+03
50% 7543.500000 1.964700e+04 364.000000 2.608150e+04
75% 11314.750000 2.087552e+05 2170.000000 2.216012e+05
max 15086.000000 4.927480e+06 83777.000000 5.433506e+06
InĀ [17]:
vaccine_df = pd.read_csv("C:\\Users\\KHUSHI\\Downloads\\Covid-19-Data-Analysis\\covid_vaccine_statewise.csv")
InĀ [19]:
vaccine_df.head()
Out[19]:
Updated On State Total Doses Administered Sessions Sites First Dose Administered Second Dose Administered Male (Doses Administered) Female (Doses Administered) Transgender (Doses Administered) ... 18-44 Years (Doses Administered) 45-60 Years (Doses Administered) 60+ Years (Doses Administered) 18-44 Years(Individuals Vaccinated) 45-60 Years(Individuals Vaccinated) 60+ Years(Individuals Vaccinated) Male(Individuals Vaccinated) Female(Individuals Vaccinated) Transgender(Individuals Vaccinated) Total Individuals Vaccinated
0 16/01/2021 India 48276.0 3455.0 2957.0 48276.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 23757.0 24517.0 2.0 48276.0
1 17/01/2021 India 58604.0 8532.0 4954.0 58604.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 27348.0 31252.0 4.0 58604.0
2 18/01/2021 India 99449.0 13611.0 6583.0 99449.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 41361.0 58083.0 5.0 99449.0
3 19/01/2021 India 195525.0 17855.0 7951.0 195525.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 81901.0 113613.0 11.0 195525.0
4 20/01/2021 India 251280.0 25472.0 10504.0 251280.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 98111.0 153145.0 24.0 251280.0

5 rows Ɨ 24 columns

InĀ [21]:
covid_df.drop(["Sno","Time" , "ConfirmedIndianNational", "ConfirmedForeignNational"], inplace = True, axis = 1)
InĀ [23]:
covid_df.head()
Out[23]:
Date State/UnionTerritory Cured Deaths Confirmed
0 2020-01-30 Kerala 0.0 0.0 1.0
1 2020-01-31 Kerala 0.0 0.0 1.0
2 2020-02-01 Kerala 0.0 0.0 2.0
3 2020-02-02 Kerala 0.0 0.0 3.0
4 2020-02-03 Kerala 0.0 0.0 3.0
InĀ [25]:
covid_df['Date'] = pd.to_datetime(covid_df['Date'], format = '%Y-%m-%d')
InĀ [27]:
covid_df.head()
Out[27]:
Date State/UnionTerritory Cured Deaths Confirmed
0 2020-01-30 Kerala 0.0 0.0 1.0
1 2020-01-31 Kerala 0.0 0.0 1.0
2 2020-02-01 Kerala 0.0 0.0 2.0
3 2020-02-02 Kerala 0.0 0.0 3.0
4 2020-02-03 Kerala 0.0 0.0 3.0
InĀ [29]:
#Active cases

covid_df['Active_Cases'] = covid_df['Confirmed'] - (covid_df['Cured'] + covid_df['Deaths'])
covid_df.tail()
Out[29]:
Date State/UnionTerritory Cured Deaths Confirmed Active_Cases
15109 NaT NaN NaN NaN NaN NaN
15110 NaT NaN NaN NaN NaN NaN
15111 NaT NaN NaN NaN NaN NaN
15112 NaT NaN NaN NaN NaN NaN
15113 NaT NaN NaN NaN NaN NaN
InĀ [31]:
statewise = pd.pivot_table(covid_df,values = ['Confirmed', 'Deaths', 'Cured'], index = 'State/UnionTerritory', aggfunc = 'max')
InĀ [33]:
statewise['Recovery Rate'] = statewise['Cured']*100/statewise['Confirmed']
InĀ [35]:
statewise['Mortality Rate'] = statewise['Deaths']*100/statewise['Confirmed']
InĀ [37]:
statewise = statewise.sort_values(by = 'Confirmed', ascending = False)
InĀ [39]:
statewise.style.background_gradient(cmap = 'cubehelix')
Out[39]:
Ā  Confirmed Cured Deaths Recovery Rate Mortality Rate
State/UnionTerritory Ā  Ā  Ā  Ā  Ā 
Maharashtra 5433506.000000 4927480.000000 83777.000000 90.686934 1.541859
Karnataka 2272374.000000 1674487.000000 22838.000000 73.688882 1.005028
Kerala 2200706.000000 1846105.000000 6612.000000 83.886944 0.300449
Tamil Nadu 1664350.000000 1403052.000000 18369.000000 84.300297 1.103674
Uttar Pradesh 1637663.000000 1483249.000000 18072.000000 90.571076 1.103524
Andhra Pradesh 1475372.000000 1254291.000000 9580.000000 85.015237 0.649328
Delhi 1402873.000000 1329899.000000 22111.000000 94.798246 1.576123
West Bengal 1171861.000000 1026492.000000 13576.000000 87.595030 1.158499
Chhattisgarh 925531.000000 823113.000000 12036.000000 88.934136 1.300443
Rajasthan 879664.000000 713129.000000 7080.000000 81.068340 0.804853
Gujarat 766201.000000 660489.000000 9269.000000 86.203098 1.209735
Madhya Pradesh 742718.000000 652612.000000 7139.000000 87.868074 0.961199
Haryana 709689.000000 626852.000000 6923.000000 88.327704 0.975498
Bihar 664115.000000 595377.000000 4039.000000 89.649684 0.608178
Odisha 633302.000000 536595.000000 2357.000000 84.729718 0.372176
Telangana 536766.000000 485644.000000 3012.000000 90.475924 0.561138
Punjab 511652.000000 427058.000000 12317.000000 83.466497 2.407300
Telengana 443360.000000 362160.000000 2312.000000 81.685312 0.521472
Assam 340858.000000 290774.000000 2344.000000 85.306491 0.687676
Jharkhand 320934.000000 284805.000000 4601.000000 88.742545 1.433628
Uttarakhand 295790.000000 214426.000000 5132.000000 72.492647 1.735015
Jammu and Kashmir 251919.000000 197701.000000 3293.000000 78.478003 1.307166
Himachal Pradesh 166678.000000 129330.000000 2460.000000 77.592724 1.475900
Goa 138776.000000 112633.000000 2197.000000 81.161728 1.583127
Puducherry 87749.000000 69060.000000 1212.000000 78.701752 1.381212
Chandigarh 56513.000000 48831.000000 647.000000 86.406667 1.144869
Tripura 42776.000000 36402.000000 450.000000 85.099121 1.051992
Manipur 40683.000000 33466.000000 612.000000 82.260404 1.504314
Meghalaya 24872.000000 19185.000000 355.000000 77.134931 1.427308
Arunachal Pradesh 22462.000000 19977.000000 88.000000 88.936871 0.391773
Nagaland 18714.000000 14079.000000 228.000000 75.232446 1.218339
Ladakh 16784.000000 15031.000000 170.000000 89.555529 1.012869
Sikkim 11689.000000 8427.000000 212.000000 72.093421 1.813671
Dadra and Nagar Haveli and Daman and Diu 9652.000000 8944.000000 4.000000 92.664733 0.041442
Cases being reassigned to states 9265.000000 0.000000 0.000000 0.000000 0.000000
Mizoram 9252.000000 7094.000000 29.000000 76.675313 0.313446
Andaman and Nicobar Islands 6674.000000 6359.000000 92.000000 95.280192 1.378484
Lakshadweep 5212.000000 3915.000000 15.000000 75.115119 0.287797
Unassigned 77.000000 0.000000 0.000000 0.000000 0.000000
Daman & Diu 2.000000 0.000000 0.000000 0.000000 0.000000
InĀ [41]:
#Top 10 active cases states

top_10_active_cases = covid_df.groupby(by = 'State/UnionTerritory').max()[['Active_Cases','Date']].sort_values(by = ['Active_Cases'],ascending = False).reset_index()
InĀ [43]:
fig = plt.figure(figsize=(16,9))

<Figure size 1600x900 with 0 Axes>
InĀ [45]:
plt.title('Top 10 states with most active cases in India', size = 25)
Out[45]:
Text(0.5, 1.0, 'Top 10 states with most active cases in India')
No description has been provided for this image
InĀ [47]:
ax = sns.barplot(data = top_10_active_cases.iloc[:10], y = 'Active_Cases', x = 'State/UnionTerritory', linewidth = 2, edgecolor ='black')
No description has been provided for this image
InĀ [49]:
#Top 10 active cases states

top_10_active_cases = covid_df.groupby(by = 'State/UnionTerritory').max()[['Active_Cases','Date']].sort_values(by = ['Active_Cases'],ascending = False).reset_index()
fig = plt.figure(figsize=(16,9))
plt.title('Top 10 states with most active cases in India', size = 25)
ax = sns.barplot(data = top_10_active_cases.iloc[:10], y = 'Active_Cases', x = 'State/UnionTerritory', linewidth = 2, edgecolor ='black')
plt.xlabel('States')
plt.ylabel('Total Active Cases')
plt.show()
No description has been provided for this image
InĀ [51]:
# Top states with highest deaths

top_10_deaths = covid_df.groupby(by = 'State/UnionTerritory').max()[['Deaths','Date']].sort_values(by = ['Deaths'], ascending = False).reset_index()

fig = plt.figure(figsize=(18,5))

plt.title('Top 10 states with most Deaths', size = 25)

ax = sns.barplot(data = top_10_deaths.iloc[:12], y = 'Deaths' , x = 'State/UnionTerritory',linewidth = 2, edgecolor = 'black')

plt.xlabel('States')
plt.ylabel('Total Death Cases')
plt.show()
No description has been provided for this image
InĀ [55]:
# Growth trend
#ERROR AARHA ISME 

fig = plt.figure(figsize = (12,6))

ax = sns.lineplot(data = covid_df[covid_df['State/UnionTerritory'].isin(['Maharashtra','Karnataka','Kerala','Tamil Nadu','Uttar Pradesh'])],
                  x = 'Date', y ='Active_Cases' , hue = 'State/UnionTerritory')

ax.set_title('Top 5 Affected States in India', size = 16)
Out[55]:
Text(0.5, 1.0, 'Top 5 Affected States in India')
No description has been provided for this image
InĀ [63]:
vaccine_df.head()
Out[63]:
Updated On State Total Doses Administered Sessions Sites First Dose Administered Second Dose Administered Male (Doses Administered) Female (Doses Administered) Transgender (Doses Administered) ... 18-44 Years (Doses Administered) 45-60 Years (Doses Administered) 60+ Years (Doses Administered) 18-44 Years(Individuals Vaccinated) 45-60 Years(Individuals Vaccinated) 60+ Years(Individuals Vaccinated) Male(Individuals Vaccinated) Female(Individuals Vaccinated) Transgender(Individuals Vaccinated) Total Individuals Vaccinated
0 16/01/2021 India 48276.0 3455.0 2957.0 48276.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 23757.0 24517.0 2.0 48276.0
1 17/01/2021 India 58604.0 8532.0 4954.0 58604.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 27348.0 31252.0 4.0 58604.0
2 18/01/2021 India 99449.0 13611.0 6583.0 99449.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 41361.0 58083.0 5.0 99449.0
3 19/01/2021 India 195525.0 17855.0 7951.0 195525.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 81901.0 113613.0 11.0 195525.0
4 20/01/2021 India 251280.0 25472.0 10504.0 251280.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 98111.0 153145.0 24.0 251280.0

5 rows Ɨ 24 columns

InĀ [65]:
vaccine_df.rename(columns = {'Updated On' : 'Vaccine_Date'}, inplace = True)
InĀ [67]:
vaccine_df.head(10)
Out[67]:
Vaccine_Date State Total Doses Administered Sessions Sites First Dose Administered Second Dose Administered Male (Doses Administered) Female (Doses Administered) Transgender (Doses Administered) ... 18-44 Years (Doses Administered) 45-60 Years (Doses Administered) 60+ Years (Doses Administered) 18-44 Years(Individuals Vaccinated) 45-60 Years(Individuals Vaccinated) 60+ Years(Individuals Vaccinated) Male(Individuals Vaccinated) Female(Individuals Vaccinated) Transgender(Individuals Vaccinated) Total Individuals Vaccinated
0 16/01/2021 India 48276.0 3455.0 2957.0 48276.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 23757.0 24517.0 2.0 48276.0
1 17/01/2021 India 58604.0 8532.0 4954.0 58604.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 27348.0 31252.0 4.0 58604.0
2 18/01/2021 India 99449.0 13611.0 6583.0 99449.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 41361.0 58083.0 5.0 99449.0
3 19/01/2021 India 195525.0 17855.0 7951.0 195525.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 81901.0 113613.0 11.0 195525.0
4 20/01/2021 India 251280.0 25472.0 10504.0 251280.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 98111.0 153145.0 24.0 251280.0
5 21/01/2021 India 365965.0 32226.0 12600.0 365965.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 132784.0 233143.0 38.0 365965.0
6 22/01/2021 India 549381.0 36988.0 14115.0 549381.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 193899.0 355402.0 80.0 549381.0
7 23/01/2021 India 759008.0 43076.0 15605.0 759008.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 267856.0 491049.0 103.0 759008.0
8 24/01/2021 India 835058.0 49851.0 18111.0 835058.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 296283.0 538647.0 128.0 835058.0
9 25/01/2021 India 1277104.0 55151.0 19682.0 1277104.0 0.0 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN 444137.0 832766.0 201.0 1277104.0

10 rows Ɨ 24 columns

InĀ [69]:
vaccine_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 7845 entries, 0 to 7844
Data columns (total 24 columns):
 #   Column                               Non-Null Count  Dtype  
---  ------                               --------------  -----  
 0   Vaccine_Date                         7845 non-null   object 
 1   State                                7845 non-null   object 
 2   Total Doses Administered             7621 non-null   float64
 3   Sessions                             7621 non-null   float64
 4    Sites                               7621 non-null   float64
 5   First Dose Administered              7621 non-null   float64
 6   Second Dose Administered             7621 non-null   float64
 7   Male (Doses Administered)            7461 non-null   float64
 8   Female (Doses Administered)          7461 non-null   float64
 9   Transgender (Doses Administered)     7461 non-null   float64
 10   Covaxin (Doses Administered)        7621 non-null   float64
 11  CoviShield (Doses Administered)      7621 non-null   float64
 12  Sputnik V (Doses Administered)       2995 non-null   float64
 13  AEFI                                 5438 non-null   float64
 14  18-44 Years (Doses Administered)     1702 non-null   float64
 15  45-60 Years (Doses Administered)     1702 non-null   float64
 16  60+ Years (Doses Administered)       1702 non-null   float64
 17  18-44 Years(Individuals Vaccinated)  3733 non-null   float64
 18  45-60 Years(Individuals Vaccinated)  3734 non-null   float64
 19  60+ Years(Individuals Vaccinated)    3734 non-null   float64
 20  Male(Individuals Vaccinated)         160 non-null    float64
 21  Female(Individuals Vaccinated)       160 non-null    float64
 22  Transgender(Individuals Vaccinated)  160 non-null    float64
 23  Total Individuals Vaccinated         5919 non-null   float64
dtypes: float64(22), object(2)
memory usage: 1.4+ MB
InĀ [71]:
vaccine_df.isnull().sum()
Out[71]:
Vaccine_Date                              0
State                                     0
Total Doses Administered                224
Sessions                                224
 Sites                                  224
First Dose Administered                 224
Second Dose Administered                224
Male (Doses Administered)               384
Female (Doses Administered)             384
Transgender (Doses Administered)        384
 Covaxin (Doses Administered)           224
CoviShield (Doses Administered)         224
Sputnik V (Doses Administered)         4850
AEFI                                   2407
18-44 Years (Doses Administered)       6143
45-60 Years (Doses Administered)       6143
60+ Years (Doses Administered)         6143
18-44 Years(Individuals Vaccinated)    4112
45-60 Years(Individuals Vaccinated)    4111
60+ Years(Individuals Vaccinated)      4111
Male(Individuals Vaccinated)           7685
Female(Individuals Vaccinated)         7685
Transgender(Individuals Vaccinated)    7685
Total Individuals Vaccinated           1926
dtype: int64
InĀ [73]:
vaccination = vaccine_df.drop(columns = ['Sputnik V (Doses Administered)','AEFI','18-44 Years (Doses Administered)','60+ Years (Doses Administered)'],axis=1)
InĀ [75]:
vaccination.head()
Out[75]:
Vaccine_Date State Total Doses Administered Sessions Sites First Dose Administered Second Dose Administered Male (Doses Administered) Female (Doses Administered) Transgender (Doses Administered) Covaxin (Doses Administered) CoviShield (Doses Administered) 45-60 Years (Doses Administered) 18-44 Years(Individuals Vaccinated) 45-60 Years(Individuals Vaccinated) 60+ Years(Individuals Vaccinated) Male(Individuals Vaccinated) Female(Individuals Vaccinated) Transgender(Individuals Vaccinated) Total Individuals Vaccinated
0 16/01/2021 India 48276.0 3455.0 2957.0 48276.0 0.0 NaN NaN NaN 579.0 47697.0 NaN NaN NaN NaN 23757.0 24517.0 2.0 48276.0
1 17/01/2021 India 58604.0 8532.0 4954.0 58604.0 0.0 NaN NaN NaN 635.0 57969.0 NaN NaN NaN NaN 27348.0 31252.0 4.0 58604.0
2 18/01/2021 India 99449.0 13611.0 6583.0 99449.0 0.0 NaN NaN NaN 1299.0 98150.0 NaN NaN NaN NaN 41361.0 58083.0 5.0 99449.0
3 19/01/2021 India 195525.0 17855.0 7951.0 195525.0 0.0 NaN NaN NaN 3017.0 192508.0 NaN NaN NaN NaN 81901.0 113613.0 11.0 195525.0
4 20/01/2021 India 251280.0 25472.0 10504.0 251280.0 0.0 NaN NaN NaN 3946.0 247334.0 NaN NaN NaN NaN 98111.0 153145.0 24.0 251280.0
InĀ [77]:
# Male vs Female Vaccination 
male = vaccination['Male(Individuals Vaccinated)'].sum()
female = vaccination['Female(Individuals Vaccinated)'].sum()
px.pie(names=['Male','Female'], values=[male,female], title = 'Male and Female Vaccination',color_discrete_sequence=px.colors.sequential.RdBu)
InĀ [79]:
# Remove rows where state = India 

vaccine = vaccine_df[vaccine_df.State!='India']
vaccine
Out[79]:
Vaccine_Date State Total Doses Administered Sessions Sites First Dose Administered Second Dose Administered Male (Doses Administered) Female (Doses Administered) Transgender (Doses Administered) ... 18-44 Years (Doses Administered) 45-60 Years (Doses Administered) 60+ Years (Doses Administered) 18-44 Years(Individuals Vaccinated) 45-60 Years(Individuals Vaccinated) 60+ Years(Individuals Vaccinated) Male(Individuals Vaccinated) Female(Individuals Vaccinated) Transgender(Individuals Vaccinated) Total Individuals Vaccinated
212 16/01/2021 Andaman and Nicobar Islands 23.0 2.0 2.0 23.0 0.0 12.0 11.0 0.0 ... NaN NaN NaN NaN NaN NaN NaN NaN NaN 23.0
213 17/01/2021 Andaman and Nicobar Islands 23.0 2.0 2.0 23.0 0.0 12.0 11.0 0.0 ... NaN NaN NaN NaN NaN NaN NaN NaN NaN 23.0
214 18/01/2021 Andaman and Nicobar Islands 42.0 9.0 2.0 42.0 0.0 29.0 13.0 0.0 ... NaN NaN NaN NaN NaN NaN NaN NaN NaN 42.0
215 19/01/2021 Andaman and Nicobar Islands 89.0 12.0 2.0 89.0 0.0 53.0 36.0 0.0 ... NaN NaN NaN NaN NaN NaN NaN NaN NaN 89.0
216 20/01/2021 Andaman and Nicobar Islands 124.0 16.0 3.0 124.0 0.0 67.0 57.0 0.0 ... NaN NaN NaN NaN NaN NaN NaN NaN NaN 124.0
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
7840 11/08/2021 West Bengal NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
7841 12/08/2021 West Bengal NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
7842 13/08/2021 West Bengal NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
7843 14/08/2021 West Bengal NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
7844 15/08/2021 West Bengal NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN

7633 rows Ɨ 24 columns

InĀ [81]:
vaccine.rename(columns ={'Total Individuals Vaccinated' : 'Total'}, inplace = True)
vaccine.head()

C:\Users\KHUSHI\AppData\Local\Temp\ipykernel_10420\802833517.py:1: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
Out[81]:
Vaccine_Date State Total Doses Administered Sessions Sites First Dose Administered Second Dose Administered Male (Doses Administered) Female (Doses Administered) Transgender (Doses Administered) ... 18-44 Years (Doses Administered) 45-60 Years (Doses Administered) 60+ Years (Doses Administered) 18-44 Years(Individuals Vaccinated) 45-60 Years(Individuals Vaccinated) 60+ Years(Individuals Vaccinated) Male(Individuals Vaccinated) Female(Individuals Vaccinated) Transgender(Individuals Vaccinated) Total
212 16/01/2021 Andaman and Nicobar Islands 23.0 2.0 2.0 23.0 0.0 12.0 11.0 0.0 ... NaN NaN NaN NaN NaN NaN NaN NaN NaN 23.0
213 17/01/2021 Andaman and Nicobar Islands 23.0 2.0 2.0 23.0 0.0 12.0 11.0 0.0 ... NaN NaN NaN NaN NaN NaN NaN NaN NaN 23.0
214 18/01/2021 Andaman and Nicobar Islands 42.0 9.0 2.0 42.0 0.0 29.0 13.0 0.0 ... NaN NaN NaN NaN NaN NaN NaN NaN NaN 42.0
215 19/01/2021 Andaman and Nicobar Islands 89.0 12.0 2.0 89.0 0.0 53.0 36.0 0.0 ... NaN NaN NaN NaN NaN NaN NaN NaN NaN 89.0
216 20/01/2021 Andaman and Nicobar Islands 124.0 16.0 3.0 124.0 0.0 67.0 57.0 0.0 ... NaN NaN NaN NaN NaN NaN NaN NaN NaN 124.0

5 rows Ɨ 24 columns

InĀ [83]:
# Most vaccinated State

max_vac = vaccine.groupby('State')['Total'].sum().to_frame('Total')
max_vac = max_vac.sort_values('Total', ascending = False)[:5]
max_vac
Out[83]:
Total
State
Maharashtra 1.403075e+09
Uttar Pradesh 1.200575e+09
Rajasthan 1.141163e+09
Gujarat 1.078261e+09
West Bengal 9.250227e+08
InĀ [85]:
fig = plt.figure(figsize=(10,5))
plt.title('Top Vaccinated States in India', size = 20)
x = sns.barplot(data = max_vac.iloc[:10],y = max_vac.Total, x = max_vac.index, linewidth=2,edgecolor = 'black',palette='rocket')
plt.xlabel('States')
plt.ylabel('Vaccination')
plt.show()

C:\Users\KHUSHI\AppData\Local\Temp\ipykernel_10420\4042747451.py:3: FutureWarning:



Passing `palette` without assigning `hue` is deprecated and will be removed in v0.14.0. Assign the `x` variable to `hue` and set `legend=False` for the same effect.
No description has been provided for this image
InĀ [90]:
fig = plt.figure(figsize=(10, 5))

# Set the title for the plot
plt.title('Least Vaccinated States in India', size=20)

# Sort the DataFrame to get the least vaccinated states (smallest values at the top)
min_vac = max_vac.sort_values(by='Total').iloc[:10]  # Assuming 'Total' is the column for vaccination counts

# Create the bar plot
x = sns.barplot(
    data=min_vac,
    y='Total',  # Column with the vaccination totals
    x=min_vac.index,  # Assuming the index contains state names
    linewidth=2,
    edgecolor='black',
    palette='rocket'
)

# Set the labels for the x and y axes
plt.xlabel('States')
plt.ylabel('Vaccination')

C:\Users\KHUSHI\AppData\Local\Temp\ipykernel_10420\259435976.py:10: FutureWarning:



Passing `palette` without assigning `hue` is deprecated and will be removed in v0.14.0. Assign the `x` variable to `hue` and set `legend=False` for the same effect.
Out[90]:
Text(0, 0.5, 'Vaccination')
No description has been provided for this image